X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftudou.py;h=7421378a8c771543b3418a7d1f54b40cacb324e1;hb=HEAD;hp=da3cd76f7591a8a9e2c39ba65a47c7855104dcae;hpb=40cf7fcbd2e30747065ca7b8bf4467a9582a4aa9;p=youtube-dl diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index da3cd76f7..7421378a8 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -3,109 +3,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - float_or_none, - unescapeHTML, -) - - -class TudouIE(InfoExtractor): - IE_NAME = 'tudou' - _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P[\w-]{11})' - _TESTS = [{ - 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', - 'md5': '140a49ed444bd22f93330985d8475fcb', - 'info_dict': { - 'id': '159448201', - 'ext': 'f4v', - 'title': '卡马乔国足开大脚长传冲吊集锦', - 'thumbnail': 're:^https?://.*\.jpg$', - 'timestamp': 1372113489000, - 'description': '卡马乔卡家军,开大脚先进战术不完全集锦!', - 'duration': 289.04, - 'view_count': int, - 'filesize': int, - } - }, { - 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', - 'info_dict': { - 'id': '117049447', - 'ext': 'f4v', - 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', - 'thumbnail': 're:^https?://.*\.jpg$', - 'timestamp': 1349207518000, - 'description': 'md5:294612423894260f2dcd5c6c04fe248b', - 'duration': 5478.33, - 'view_count': int, - 'filesize': int, - } - }] - - _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' - - def _url_for_id(self, video_id, quality=None): - info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id) - if quality: - info_url += '&hd' + quality - xml_data = self._download_xml(info_url, video_id, "Opening the info XML page") - final_url = xml_data.text - return final_url - - def _real_extract(self, url): - video_id = self._match_id(url) - item_data = self._download_json( - 'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id) - - youku_vcode = item_data.get('vcode') - if youku_vcode: - return self.url_result('youku:' + youku_vcode, ie='Youku') - - title = unescapeHTML(item_data['kw']) - description = item_data.get('desc') - thumbnail_url = item_data.get('pic') - view_count = int_or_none(item_data.get('playTimes')) - timestamp = int_or_none(item_data.get('pt')) - - segments = self._parse_json(item_data['itemSegs'], video_id) - # It looks like the keys are the arguments that have to be passed as - # the hd field in the request url, we pick the higher - # Also, filter non-number qualities (see issue #3643). - quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), - key=lambda k: int(k))[-1] - parts = segments[quality] - result = [] - len_parts = len(parts) - if len_parts > 1: - self.to_screen('%s: found %s parts' % (video_id, len_parts)) - for part in parts: - part_id = part['k'] - final_url = self._url_for_id(part_id, quality) - ext = (final_url.split('?')[0]).split('.')[-1] - part_info = { - 'id': '%s' % part_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - 'description': description, - 'view_count': view_count, - 'timestamp': timestamp, - 'duration': float_or_none(part.get('seconds'), 1000), - 'filesize': int_or_none(part.get('size')), - 'http_headers': { - 'Referer': self._PLAYER_URL, - }, - } - result.append(part_info) - - return { - '_type': 'multi_video', - 'entries': result, - 'id': video_id, - 'title': title, - } class TudouPlaylistIE(InfoExtractor):